tech-lead-skill 5.5.3 → 5.5.5

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -31,6 +31,11 @@ goal -> constraints/assumptions -> L0/L1/L2 plan -> execute -> observe evidence
31
31
 
32
32
  ## Install
33
33
 
34
+ Pick your edition:
35
+
36
+ - **Prose skill for any agent environment** (opencode / Claude Code / Codex) → `tech-lead-skill`
37
+ - **DSH plugin with machine-checked read-only tools** → `dsh-themis`
38
+
34
39
  ### npm (GitHub-hosted, no registry account needed)
35
40
 
36
41
  ```bash
@@ -50,14 +55,16 @@ The installer is idempotent: repeated runs back up existing files as `*.bak-<tim
50
55
 
51
56
  ### DeepSeek Harness plugin (read-only tools)
52
57
 
53
- Ships on the DSH plugin market (npm) as ONE self-contained package, **`dsh-themis`** — named after the goddess of divine order: gates as verdicts, evidence weighed, releases audited. Install into any profile:
58
+ **For DSH users:** ships on the DSH plugin market (npm) as ONE self-contained package, **`dsh-themis`** — named after the goddess of divine order: gates as verdicts, evidence weighed, releases audited. Install into any profile:
54
59
 
55
- ```
60
+ ```bash
56
61
  dsh plugin --profile headless add dsh-themis
57
62
  ```
58
63
 
59
64
  22 registered entry points in a single artifact: 21 read-only governance tools plus a capability-discovery tool (`tech_lead_capabilities`) that lists only what this bundle actually registers (the original nine audits plus context validation, evidence graph/freshness analysis, progress decisions, critical-path/impact analysis, resume reconciliation, gate planning/aggregation/reopen checks, and mutation preview). Tools compute over caller-supplied JSON only — no filesystem writes, no subprocesses, no network access. The earlier split packages (`dsh-tech-lead-{core,plugin,bundle}`) are deprecated in favor of this one. Source checkouts remain supported: build via `node scripts/build-market-package.mjs` then `dsh plugin add packages/dsh-themis`. The root npm package distributes the skill and installer only.
60
65
 
66
+ **Two artifacts, one rulebook:** `tech-lead-skill` is the conservative, broadly-compatible prose spec — install it into any agent environment (opencode, Claude Code, Codex) and nothing else is required. **`dsh-themis` is the DSH-plugin specialized edition**: the same judgment layer plus a machine-checked read-only runtime — schema-declared `protocolJson` negotiation on all 22 tools (bare legacy by default, explicit v1/v2 envelopes, fail-closed on unknown selections), one-way state→context-v2 projection that never invents identity or provenance, strict/compat input handling, and stable v2 envelopes (`findings`, `guidance`, `meta.complete`, `meta.outputProtocol`).
67
+
61
68
  ```bash
62
69
  dsh plugin --profile headless add /path/to/tech-lead-skill/packages/dsh-themis
63
70
  dsh --profile headless --dump-config # verify the tech-lead-tools row is present
@@ -148,6 +155,6 @@ The executable skill body (`SKILL.md`) is authored in Simplified Chinese; coding
148
155
 
149
156
  ## Version
150
157
 
151
- Current version: `v5.5.3`.
158
+ Current version: `v5.5.5`.
152
159
 
153
160
  See [`docs/TECHNICAL_GUIDE.md`](docs/TECHNICAL_GUIDE.md) for the full operating model and [`docs/AUDIT_REPORT.md`](docs/AUDIT_REPORT.md) for the publication audit.
package/README.zh-CN.md CHANGED
@@ -31,6 +31,11 @@
31
31
 
32
32
  ## 安装
33
33
 
34
+ 先选版本:
35
+
36
+ - **纯文本规范,任意 agent 环境**(opencode / Claude Code / Codex)→ `tech-lead-skill`
37
+ - **带机器可校验只读工具的 DSH 插件** → `dsh-themis`
38
+
34
39
  ### npm 方式(GitHub 源,无需注册账号)
35
40
 
36
41
  ```bash
@@ -50,7 +55,7 @@ npx github:240xu/tech-lead-skill
50
55
 
51
56
  ### DeepSeek Harness 插件(只读工具)
52
57
 
53
- 已上架 DSH 插件市场(npm)——**单一自包含包**,任意 profile 一键安装:
58
+ **DSH 用户看这里:** 已上架 DSH 插件市场(npm)——**单一自包含包**,任意 profile 一键安装:
54
59
 
55
60
  ```
56
61
  dsh plugin --profile headless add dsh-themis
@@ -58,6 +63,8 @@ dsh plugin --profile headless add dsh-themis
58
63
 
59
64
  单包注册 22 个入口:21 个只读治理工具(原九项审计+上下文校验、证据图/新鲜度分析、推进决策、关键路径/影响分析、续跑对账、Gate 计划/聚合/重开、变更预览)+能力发现工具 `tech_lead_capabilities`(只列出本包实际注册的工具)。仅对调用方传入的 JSON 做计算——无文件写入、无子进程、无网络访问。旧拆分包(`dsh-tech-lead-{core,plugin,bundle}`)已弃用并指向本包。源码安装:`node scripts/build-market-package.mjs` 装配后 `dsh plugin add packages/dsh-themis`。根 npm 包只发布技能与安装器。
60
65
 
66
+ **两个产物,同一套规范:** `tech-lead-skill` 是保守、广泛兼容的纯文本规范——装进任何 agent 环境(opencode/Claude Code/Codex)即可,无其他依赖。**`dsh-themis` 是 DSH 插件专项优化版**:同样的判断层外加机器可校验的只读运行时——全部 22 工具在 schema 中声明 `protocolJson`(legacy 默认裸形态、显式请求 v1/v2 信封、未知取值 fail-closed)、state→context-v2 单向投影(身份与来源永不虚构)、strict/compat 输入兼容模式,以及稳定的 v2 信封(`findings`/`guidance`/`meta.complete`/`meta.outputProtocol`)。
67
+
61
68
  ```bash
62
69
  dsh plugin --profile headless add /path/to/tech-lead-skill/packages/dsh-themis
63
70
  dsh --profile headless --dump-config # 确认 tech-lead-tools 行已注入
@@ -148,6 +155,6 @@ dsh --profile headless --dump-config # 确认 tech-lead-tools 行已注入
148
155
 
149
156
  ## 版本
150
157
 
151
- 当前版本:`v5.5.3`.
158
+ 当前版本:`v5.5.5`.
152
159
 
153
160
  完整运行模型见[技术指南](./docs/TECHNICAL_GUIDE.zh-CN.md),发布审计见 [docs/AUDIT_REPORT.md](docs/AUDIT_REPORT.md)。
@@ -35,7 +35,7 @@ The source set was scanned for local absolute paths, passwords, API-key prefixes
35
35
  ### Structural scan
36
36
 
37
37
  - YAML frontmatter has `name: tech-lead` and a trigger description.
38
- - The skill version is `v5.5.3`. R8.1 (2026-08-26) completes the R8 public contract: protocolJson declared on all 22 tool schemas; all nine legacy bare tools negotiate with bare defaults and fail-closed envelope passthrough; inputCompatibility=compat migrates unknown context keys instead of rejecting; context_validate dispatches canonical v2 documents to validateContextV2; v2 envelopes carry findings/guidance/meta.complete plus meta.outputProtocol stamped by negotiation. one-way state→context-v2 projection (identity options mandatory), result-protocol negotiation on every tool, and the v2 wire label for strengthened envelopes; reverse projection is deferred as non-lossless (evidence/2026-08-26-r8-projection.md).
38
+ - The skill version is `v5.5.5`. R8.1 (2026-08-26) completes the R8 public contract: protocolJson declared on all 22 tool schemas; all nine legacy bare tools negotiate with bare defaults and fail-closed envelope passthrough; inputCompatibility=compat migrates unknown context keys instead of rejecting; context_validate dispatches canonical v2 documents to validateContextV2; v2 envelopes carry findings/guidance/meta.complete plus meta.outputProtocol stamped by negotiation. one-way state→context-v2 projection (identity options mandatory), result-protocol negotiation on every tool, and the v2 wire label for strengthened envelopes; reverse projection is deferred as non-lossless (evidence/2026-08-26-r8-projection.md).
39
39
  - The eight templates referenced by the skill exist.
40
40
  - The installer validates options, requires a marker before removing any target, and records the managed package/version after installation.
41
41
  - The release-check template covers allowlist inventory, sensitive-content scanning, reference checks, scope checks, publication results, and remote verification.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "tech-lead-skill",
3
- "version": "5.5.3",
3
+ "version": "5.5.5",
4
4
  "description": "Evidence-driven planning and safe change-control skill for OpenCode-compatible agents",
5
5
  "license": "MIT",
6
6
  "repository": {
package/skill/SKILL.md CHANGED
@@ -3,7 +3,7 @@ name: tech-lead
3
3
  description: 用于软件、基础设施、研究和运维中的多步、跨边界或有状态工程交付:项目规划、架构选择、跨模块实现、部署、迁移、发布、恢复、重构、长期运行与跨会话续跑。涉及不可逆/生产变更、回滚验证、真实环境对账、发布安全或项目级交付治理时优先加载,即使用户没有说“项目”或“Tech Lead”。不要仅因一次性小修复、单文件编辑、普通解释、单次测试或只读代码审查而自动加载,除非用户明确要求项目级计划或本规范。
4
4
  ---
5
5
 
6
- # Tech Lead · 自主演进规划与交付规范 v5.5.3
6
+ # Tech Lead · 自主演进规划与交付规范 v5.5.5
7
7
 
8
8
  > 双层架构声明:本文件是**判断层**(自由裁量域)。其中可机械判定的不变量(Gate 前置校验、
9
9
  > 证据锚点存在性、分级判定器、状态机转换有效性)为未来 **MCP 工具化候选**——